The aim is to uncover the perspectives of Twitter users on Multiple Sclerosis (MS) in English tweets by: (i) determining the sentiment of the text (ii) identifying the discussed topics.
Methods
The tweets were scanned in April 2023 using the keywords “multiple sclerosis, multiplesclerosis”. Artificial intelligence-based sentiment analysis was conducted on a total of 1168 tweets and content analysis was performed on 17.4% of these tweets.
Results
Tweets of 44% are positive and 22.3% are negative sentiment. As a result of content analysis, three themes and their sub-themes were identified: (i) announcement sharing: invitation to support, promotion of academic publications, (ii) information sharing: information providers, information seekers, news providers, (iii) experience sharing: challenging MS, facilitated MS, emotionally impactful MS, comparative MS, misunderstood MS. Subjective content such as experiences is shared less frequently compared to objective content such as announcements and information.
Discussion
The findings of this study can serve as a guiding factor in supporting positive views, managing negative views, and promoting the expression of subjective experiences.
LavorgnaLLanzilloRMorraVB, et al.Social media and multiple sclerosis in the posttruth age. Interact J Med Res2017; 6: e7879.
2.
FarpourHRHoveidaeiAHHabibiL, et al.The impact of social media use on depression in multiple sclerosis patients. Acta Neurol Belg2020; 120: 1405–1409.
3.
EijkholtMSparlingA. Health, honesty and happiness: authenticity and anonymity in social media participation of individuals with multiple sclerosis. Mult Scler Relat Disord2019; 27: 121–126.
4.
UsluEYıldırımN. Picture of multiple sclerosis studies in nursing: a bibliometric study. Turk J Neurol2024; 30: 244–253.
5.
KantorDBrightJRBurtchellJ. Perspectives from the patient and the healthcare professional in multiple sclerosis: social media and participatory medicine. Neurol Ther2018; 7: 37–49.
6.
NawarNEl-GayarOAmbatiLS, et al.Social media for exploring adverse drug events associated with multiple sclerosis. In: Proceedings of the 55th Hawaii International Conference on System Sciences, 2022, pp.4217–4226.
7.
RamagopalanSVWasiakRCoxAP. Using Twitter to investigate opinions about multiple sclerosis treatments: a descriptive, exploratory study. F1000Res2014; 3: 16.
8.
RezaallahBLewisDJPierceC, et al.Social media surveillance of multiple sclerosis medications used during pregnancy and breastfeeding: content analysis. J Med Internet Res2019; 21: e13003.
9.
MokhberdezfuliMSahrianMAMoghadasiAN. Use of social Media tools during COVID-19 pandemic among MS fellowships and patients. Mult Scler Relat Disord2023; 71: 104299.
10.
NesbittCRathLYehWZ, et al.MSCOVID19: using social media to achieve rapid dissemination of health information. Mult Scler Relat Disord2020; 45: 102338.
11.
DongXLianY. A review of social media-based public opinion analyses: challenges and recommendations. Technol Soc2021; 67: 101724.
12.
SinnenbergLButtenheimAMPadrezK, et al.Twitter as a tool for health research: a systematic review. Am J Public Health2017; 107: e1–e8.
13.
GündüzUDemirelS. Metaverse-related perceptions and sentiments on Twitter: evidence from text mining and network analysis: metaverse-related perceptions and sentiments on Twitter. Electron Commer Res2025; 25: 1453–1483.
14.
DemirelSKahramanEGündüzU. A text mining analysis of the change in status of the Hagia Sophia on Twitter: the political discourse and its reflections on the public opinion. Atl J Commun2024; 32: 63–90.
15.
DemirelSKahraman-GokalpEGündüzU. From optimism to concern: unveiling sentiments and perceptions surrounding ChatGPT on Twitter. Int J Hum–Comput Interact2025; 41: 7292–7314.
16.
KahramanEDemirelSGündüzU. COVID-19 vaccines in twitter ecosystem: analyzing perceptions and attitudes by sentiment and text analysis method. J Public Health2025; 33: 965–979.
17.
AlankaD. Content analysis as a qualitative research method: a theoretical framework. Kronotop J Commun2024; 1: 64–84.
18.
GiuntiGClaesMDorronzoro ZubieteE, et al.Analysing sentiment and topics related to multiple sclerosis on Twitter. Med Inf Eur2020; 270: 911–915.
19.
GiuntiGClaesMZubieteED, et al.Impact of covid-19 on multiple sclerosis topic discussion on twitter. In: Public Health and Informatics: Proceedings of MIE 2021. SAGE Publications; 2021:865-869.
ChaudharyJNivedithaS. Twitter sentiment analysis using tweepy. Int Res J Eng Tech2021; 8: 4512–4516.
22.
ColaizziPF. Existential phenomenological alternatives for psychology. New York, NY, USA: Psychological Research as the Phenomenologist Views It/Oxford University Press, 1978.
23.
RatheeNJoshiNKaurJ. Sentiment analysis using machine learning techniques on python. In: 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), 2018, pp.779–785: IEEE.
24.
ThakurNCuiSKhannaK, et al.Investigation of the gender-specific discourse about online learning during COVID-19 on Twitter using sentiment analysis, subjectivity analysis, and toxicity analysis. Computers2023; 12: 21.
25.
Fosch-VillarongaEPoulsenASøraaRA, et al.A little bird told me your gender: gender inferences in social media. Inf Process Manag2021; 58: 102541.
26.
UsluEYıldırımN. Wondering about multiple sclerosis: google trends data. Gümüşhane Univ J Health Sci2024; 13: 736–742.
27.
DikeçGObanVUstaMB. Qualitative and artificial intelligence-based sentiment analysis of Turkish tweets related to schizophrenia. Turk J Psychiatry2023; 34: 145–153.
28.
TongASainsburyPCraigJ. Consolidated criteria for reporting qualitative research (COREQ): a 32-item checklist for interviews and focus groups. J Healthc Qual2007; 19: 349–357.
29.
FranzkeASMuisISchäferMT. Data ethics decision aid (DEDA): a dialogical framework for ethical inquiry of AI and data projects in The Netherlands. Ethics Inf Technol2021; 23: 1–17.
MenculiniGManciniAGaetaniL, et al.Psychiatric symptoms in multiple sclerosis: a biological perspective on synaptic and network dysfunction. J Neurol Neurosurg Psychiatry2023; 94: 389–395.
32.
ErskineNHendricksS. The use of twitter by medical journals: systematic review of the literature. J Med Internet Res2021; 23: e26378.
33.
World Multiple Sclerosis Day. The MS Connections Campaign: World MS Day 30 May, https://worldmsday.org/about/ (accessed 10 July 2024).
34.
Kahraman-GokalpEDemirelSGündüzU. Exploring the surge of negativity during the COVID-19 pandemic: computational text and sentiment analysis across eight newsrooms’ tweets. Atl J Commun2024; 32: 298–324.
35.
McCabeMPEbacioniKJSimmonsR, et al.Unmet education, psychological and peer support needs of people with multiple sclerosis. J Psychosom Res2015; 78: 82–87.
36.
SynnotAJHillSJGarnerKA, et al.Online health information seeking: how people with multiple sclerosis find, assess and integrate treatment information to manage their health. Health Expect2016; 19: 727–737.
37.
VitturiBKRahmaniADiniG, et al.Stigma, discrimination and disclosure of the diagnosis of multiple sclerosis in the workplace: a systematic review. Int J Environ Res Public Health2022; 19: 9452.
38.
LloydA. Social media, help or hindrance: what role does social media play in young people's mental health?Psychiatr Danub2014; 26: 340–346.
39.
UsluEÖzsabanAOcakŞ, et al.Patient perspectives about multiple sclerosis: a metaphor study. J Eval Clin Pract2024; 30: 687–692.
40.
BrownleeWJHardyTAFazekasF, et al.Diagnosis of multiple sclerosis: progress and challenges. Lancet2017; 389: 1336–1346.
41.
TopcuGMhizha-MuriraJRGriffithsH, et al.Experiences of receiving a diagnosis of multiple sclerosis: a meta-synthesis of qualitative studies. Disabil Rehabil2023; 45: 772–783.
